Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Java code/documentation

    np_max-act · gemini-2.0-flash

    The neuron fires on Javadoc author tags (the “@author” lines with author names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     preload
    -0.07
    raquo
    -0.07
     corr
    -0.07
    Scale
    -0.07
    .eu
    -0.07
     Hakk
    -0.07
     ＿
    -0.07
     semp
    -0.06
    ”.↵↵
    -0.06
    Sorted
    -0.06
    POSITIVE LOGITS
     Gi�
    0.06
    村
    0.06
    ographer
    0.06
    Nos
    0.05
     Nem
    0.05
    igen
    0.05
     uLocal
    0.05
    uluğu
    0.05
     smell
    0.05
    ā
    0.05
    Act Density 0.008%

    No Known Activations